利用边特征增强因果信号，改善图分类中的标签不平衡问题。
Catch Causal Signals from Edges for Label Imbalance in Graph Classification
- 通过边信息增强因果注意力机制，分离因果子图
- 在PTC、Tox21等数据集上显著提升分类准确率
- 适合处理图级别标签不平衡任务的研究者使用
尽管图结构上的因果研究已取得进展并应用于解决标签不平衡问题，但边特征在检测图内因果效应中的作用仍被忽视，导致现有方法尚未充分发挥潜力。本文通过有效利用边信息，增强因果注意力机制，以解耦原始图中的因果子图，并进一步利用边特征重塑图表示。该设计捕获了更全面的因果信号，在存在标签不平衡的图分类任务中表现更优。我们在PTC、Tox21和ogbg-molhiv等真实世界数据集上评估了该方法，结果优于多个基线模型。研究表明，边特征在图因果检测中至关重要，为解决图级别任务中的标签不平衡问题提供了新方向。代码与实现细节见https://github.com/fengrui-z/ECAL。
原文摘要 · Abstract (English)
Despite significant advancements in causal research on graphs and its application to cracking label imbalance, the role of edge features in detecting the causal effects within graphs has been largely overlooked, leaving existing methods with untapped potential for further performance gains. In this paper, we enhance the causal attention mechanism through effectively leveraging edge information to disentangle the causal subgraph from the original graph, as well as further utilizing edge features to reshape graph representations. Capturing more comprehensive causal signals, our design leads to improved performance on graph classification tasks with label imbalance issues. We evaluate our approach on real-word datasets PTC, Tox21, and ogbg-molhiv, observing improvements over baselines. Overall, we highlight the importance of edge features in graph causal detection and provide a promising direction for addressing label imbalance challenges in graph-level tasks. The model implementation details and the codes are available on https://github.com/fengrui-z/ECAL
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。